Search

The aim of the proposed work is to predict the performance of the Artificial Neural Network (ANN) algorithm in detection of novel car quality performance by comparing it with the Decision tree algorithm. Materials and Methods: Proposed work uses a total sample size of 1556 dataset collected from UCI repository with accurate quality 778 samples and inaccurate 778 samples. The collected samples are divided into two groups, group 1 with training data (n = 1167 [75%]) and group 2 with testing data (n = 389 [25%]). Calculation of samples is done by using G power analysis with clincalc which contains two different groups, alpha (0.05), power (80%) and environment ratio. Results: In the proposed model ANN algorithm achieved accuracy, recall and precision of 94.09%, 97.95%, and 95.21% respectively compared to 92.25%, 96.81% and 93.34% by Decision tree algorithm. The obtained significance value of this analysis is 0.000. Conclusion: For the given dataset, the ANN shows significantly better results than the Decision tree algorithm in the car acceptability evaluation. [ABSTRACT FROM AUTHOR]